INDEX

Explanations

instances where events or situations are followed by commentary or consequences

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

heit

-0.79

AppData

-0.76

nexus

-0.75

gans

-0.75

=-=-=-=-

-0.74

||||

-0.71

ãĤ¤ãĥĪ

-0.70

Condition

-0.68

kept

-0.68

abouts

-0.67

POSITIVE LOGITS

 resignation

1.30

 announcement

1.26

 revelations

1.15

 massacre

1.14

 revelation

1.11

 tragic

1.08

 fatal

1.07

 deadly

1.06

 publication

1.05

 acqu

1.05

Activations Density 0.260%

instances where events or situations are followed by commentary or consequences

No Comments

No Known Activations